Lexical Semantics

1
Lexical Semantics Word Sense Disambiguation

• CMSC 35100
• Natural Language Processing
• May 15, 2003

2
Roadmap

• Lexical Semantics
• Emergent Meaning
• Thematic roles, Frames, Primitives
• Word Sense Disambiguation
• Selectional Restriction-based approaches
• Limitations
• Robust Approaches
• Supervised Learning Approaches
• Naïve Bayes
• Bootstrapping Approaches
• One sense per discourse/collocation
• Unsupervised Approaches
• Schutzes word space
• Resource-based Approaches
• Dictionary parsing, WordNet Distance
• Why they work
• Why they dont

3
Word-internal Structure

• Thematic roles
• Characterize verbs by their arguments
• E.g. transport agent, theme, source, destination
• They transported grain from the fields to the
  silo.
• Deep structure passive / active same roles
• Thematic hierarchy
• E.g. agent gt theme gt source, dest
• Provide default surface positions
• Tie to semantics (e.g. Levin) Interlinguas
• Cluster verb meanings by set of syntactic
  alternations
• Limitations only NP,PP other arguments
  predicates less

4
Selectional Restrictions

• Semantic constraints on filling of roles
• E.g. Bill ate chicken
• Eat Agent animate Theme Edible
• Associate with sense
• Most commonly of verb/event possibly adj, noun
• Specifying constraints
• Add a term to semantics, e.g. Isa(x,Ediblething)
• Tie to position in WordNet
• All hyponyms inherit

5
Primitive Decompositions

• Jackendoff(1990), Dorr(1999), McCawley (1968)
• Word meaning constructed from primitives
• Fixed small set of basic primitives
• E.g. cause, go, become,
• killcause X to become Y
• Augment with open-ended manner
• Y not alive
• E.g. walk vs run
• Fixed primitives/Infinite descriptors

6
Word Sense Disambiguation

• Application of lexical semantics
• Goal Given a word in context, identify the
  appropriate sense
• E.g. plants and animals in the rainforest
• Crucial for real syntactic semantic analysis
• Correct sense can determine
• Available syntactic structure
• Available thematic roles, correct meaning,..

7
Selectional Restriction Approaches

• Integrate sense selection in parsing and semantic
  analysis e.g. with Montague
• Concept Predicate selects sense
• Washing dishes vs stir-frying dishes
• Stir-fry patient food gt dishfood
• Serve Denver vs serve breakfast
• Serve vegetarian dishes
• Serve1 patient loc serve1 patient food
• gt dishesfood only valid variant
• Integrate in rule-to-rule test e.g. in WN

8
Selectional Restrictions Limitations

• Problem 1 Predicates too general
• Recommend, like, hit.
• Problem 2 Language too flexible
• The circus performer ate fire and swallowed
  swords
• Unlikely but doable
• Also metaphor
• Strong restrictions would block all analysis
• Some approaches generalize up hierarchy
• Can over-accept truly weird things

9
Robust Disambiguation

• More to semantics than P-A structure
• Select sense where predicates underconstrain
• Learning approaches
• Supervised, Bootstrapped, Unsupervised
• Knowledge-based approaches
• Dictionaries, Taxonomies
• Widen notion of context for sense selection
• Words within window (2,50,discourse)
• Narrow cooccurrence - collocations

10
Disambiguation Features

• Key What are the features?
• Part of speech
• Of word and neighbors
• Morphologically simplified form
• Words in neighborhood
• Question How big a neighborhood?
• Is there a single optimal size? Why?
• (Possibly shallow) Syntactic analysis
• E.g. predicate-argument relations, modification,
  phrases
• Collocation vs co-occurrence features
• Collocation words in specific relation p-a, 1
  word /-
• Co-occurrence bag of words..

11
Naïve Bayes Approach

• Supervised learning approach
• Input feature vector X label
• Best sense most probable sense given V
• Naïve assumption features independent

12
Example Plant Disambiguation
There are more kinds of plants and animals in
the rainforests than anywhere else on Earth. Over
half of the millions of known species of plants
and animals live in the rainforest. Many are
found nowhere else. There are even plants and
animals in the rainforest that we have not yet
discovered. Biological Example The Paulus
company was founded in 1938. Since those days the
product range has been the subject of constant
expansions and is brought up continuously to
correspond with the state of the art. Were
engineering, manufacturing and commissioning
world- wide ready-to-run plants packed with our
comprehensive know-how. Our Product Range
includes pneumatic conveying systems for carbon,
carbide, sand, lime and many others. We use
reagent injection in molten metal for
the Industrial Example Label the First Use of
Plant
13
Yarowskys Decision Lists Detail

• One Sense Per Discourse - Majority
• One Sense Per Collocation
• Near Same Words

Same Sense
14
Yarowskys Decision Lists Detail

• Training Decision Lists
• 1. Pick Seed Instances Tag
• 2. Find Collocations Word Left, Word Right, Word
  K
• (A) Calculate Informativeness on Tagged Set,
• Order
• (B) Tag New Instances with Rules
• (C) Apply 1 Sense/Discourse
• (D) If Still Unlabeled, Go To 2
• 3. Apply 1 Sense/Discouse
• Disambiguation First Rule Matched

15
Sense Choice With Collocational Decision Lists

• Use Initial Decision List
• Rules Ordered by
• Check nearby Word Groups (Collocations)
• Biology Animal in 2-10 words
• Industry Manufacturing in 2-10 words
• Result Correct Selection
• 95 on Pair-wise tasks

16
Semantic Ambiguity

• Plant ambiguity
• Botanical vs Manufacturing senses
• Two types of context
• Local 1-2 words away
• Global several sentence window
• Two observations (Yarowsky 1995)
• One sense per collocation (local)
• One sense per discourse (global)

17
Schutzes Vector Space Detail

• Build a co-occurrence matrix
• Restrict Vocabulary to 4 letter sequences
• Exclude Very Frequent - Articles, Affixes
• Entries in 5000-5000 Matrix
• Word Context
• 4grams within 1001 Characters
• Sum Normalize Vectors for each 4gram
• Distances between Vectors by dot product

97 Real Values
18
Schutzes Vector Space continued

• Word Sense Disambiguation
• Context Vectors of All Instances of Word
• Automatically Cluster Context Vectors
• Hand-label Clusters with Sense Tag
• Tag New Instance with Nearest Cluster

19
Sense Selection in Word Space

• Build a Context Vector
• 1,001 character window - Whole Article
• Compare Vector Distances to Sense Clusters
• Only 3 Content Words in Common
• Distant Context Vectors
• Clusters - Build Automatically, Label Manually
• Result 2 Different, Correct Senses
• 92 on Pair-wise tasks

20
Resniks WordNet Labeling Detail

• Assume Source of Clusters
• Assume KB Word Senses in WordNet IS-A hierarchy
• Assume a Text Corpus
• Calculate Informativeness
• For Each KB Node
• Sum occurrences of it and all children
• Informativeness
• Disambiguate wrt Cluster WordNet
• Find MIS for each pair, I
• For each subsumed sense, Vote I
• Select Sense with Highest Vote

21
Sense Labeling Under WordNet

• Use Local Content Words as Clusters
• Biology Plants, Animals, Rainforests, species
• Industry Company, Products, Range, Systems
• Find Common Ancestors in WordNet
• Biology Plants Animals isa Living Thing
• Industry Product Plant isa Artifact isa Entity
• Use Most Informative
• Result Correct Selection

22
The Question of Context

• Shared Intuition
• Context
• Area of Disagreement
• What is context?
• Wide vs Narrow Window
• Word Co-occurrences

Sense
23
Taxonomy of Contextual Information

• Topical Content
• Word Associations
• Syntactic Constraints
• Selectional Preferences
• World Knowledge Inference

24
A Trivial Definition of ContextAll Words within
X words of Target

• Many words Schutze - 1000 characters, several
  sentences
• Unordered Bag of Words
• Information Captured Topic Word Association
• Limits on Applicability
• Nouns vs. Verbs Adjectives
• Schutze Nouns - 92, Train -Verb, 69

25
Limits of Wide Context

• Comparison of Wide-Context Techniques (LTV 93)
• Neural Net, Context Vector, Bayesian Classifier,
  Simulated Annealing
• Results 2 Senses - 90 3 senses 70
• People Sentences 100 Bag of Words 70
• Inadequate Context
• Need Narrow Context
• Local Constraints Override
• Retain Order, Adjacency

26
Surface Regularities Useful Disambiguators

• Not Necessarily!
• Scratching her nose vs Kicking the bucket
  (deMarcken 1995)
• Right for the Wrong Reason
• Burglar Rob Thieves Stray Crate Chase Lookout
• Learning the Corpus, not the Sense
• The Ste. Cluster Dry Oyster Whisky Hot Float
  Ice
• Learning Nothing Useful, Wrong Question
• Keeping Bring Hoping Wiping Could Should Some
  Them Rest

27
Interactions Below the Surface

• Constraints Not All Created Equal
• The Astronomer Married the Star
• Selectional Restrictions Override Topic
• No Surface Regularities
• The emigration/immigration bill guaranteed
  passports to all Soviet citizens
• No Substitute for Understanding

28
What is Similar

• Ad-hoc Definitions of Sense
• Cluster in word space, WordNet Sense, Seed
  Sense Circular
• Schutze Vector Distance in Word Space
• Resnik Informativeness of WordNet Subsumer
  Cluster
• Relation in Cluster not WordNet is-a hierarchy
• Yarowsky No Similarity, Only Difference
• Decision Lists - 1/Pair
• Find Discriminants